© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14933
    Prev
    Next
    INDEX
    Explanations

    relationships and structures in assembly language instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Koy
    -0.63
    ỡng
    -0.62
    parsedMessage
    -0.59
     pymongo
    -0.57
     survey
    -0.56
     questionnaire
    -0.54
    Survey
    -0.52
     khảo
    -0.52
    Volumen
    -0.52
     questionnaires
    -0.52
    POSITIVE LOGITS
     instruction
    1.28
     Instruction
    1.13
    instruction
    1.05
     instructions
    1.04
    Instruction
    1.01
     Instructions
    0.95
    instructions
    0.93
     INSTRUCTION
    0.91
     INSTRUCTIONS
    0.86
    Instructions
    0.85
    Activations Density 1.029%

    No Known Activations